Innovative Projects Realized

Deep-learning cross-modality super-resolution imaging of the cellular network in bone

Many organisms, such as bone, depend on fluid-filled network structures for cellular transport, signaling and mechanosensing. Bone is made of a network called the lacunocanalicular network (LCN), which consists of lacunae that house osteocyte cells connected together by a network of 300-nm wide canals called canaliculi. An understanding of this vast network is incredibly important and could provide valuable insight into bone function and disease. While many techniques exist to visualize LCN, the large size of the network makes acquiring images at sufficient resolution while covering a large field of view difficult.

The proposed research aims to use and develop deep learning image-to-image translation to improve the resolution of microscopic images of bone and enable graph network extraction of the LCN directly from low-resolution (LR) images. It is hypothesized that deep learning can be used to perform same-modality super-resolution (SR) of LR confocal microscope images, as well as cross-modality SR of LR confocal microscope images to high-resolution Focused Ion Beam-Scanning Electron Microscopy (FIB-SEM), and to directly extract large area graph networks more efficiently.

Analyse en temps réel de signes vitaux grâce à l’application de techniques d’apprentissage automatique et à la synchronisation d’une pluralité de senseurs physiologiques

La photopléthysmographie (PPG) est une méthode non invasive mesurant les changements de volume sanguin
dans les tissus. Cette technique permet de dériver des métriques physiologiques importantes, telles que la
fréquence cardiaque, la saturation en oxygène et la pression artérielle. Cependant, pour des résultats fiables, il
est crucial de prendre en compte les différences physiologiques des individus, notamment relié à la couleur de
peau, au sexe ainsi qu’à l’âge et de surmonter les problèmes d’artefacts de mouvement.
Le projet vise à améliorer la fiabilité des métriques PPG en utilisant l’IA et un nouveau capteur portable de SiFi
Laboratoires pour améliorer la précision de la mesure de la pression artérielle en télémédecine. L’intégration de
ces technologies de pointe permettra d’obtenir des mesures de pression artérielle plus précises, ce qui peut avoir
des implications significatives pour la surveillance à distance de la santé des patients, en particulier pour les
personnes atteintes d’hypertension artérielle.

Totem-Pole PFC using Cascaded GaN Switches

The proposed project will be a collaboration between the Ottawa (ON) based integrated circuit (IC) company, Power Integrations Inc. (PI) and RIGA lab at University of Manitoba, Winnipeg (MB). The result of the research project will be transferred to the IC design team in PI to integrate power semiconductors, gate drivers, controllers
company to identify the challenges and opportunities of using GaN power semiconductors in their other new power IC products. And then their products can help other power electronics (PE) companies to reduce power losses and the society to achieve electrification. Thus, it will benefit both IC manufacturers and power electronics companies. Further, one PhD HQP will be trained in PE technologies and will be able to contribute to Canadian PE industry in the future.

Développement de modèles de prédiction et de contrôle de composition chimique et de largeur de bain dans un four de réduction

L’industrie minière est un secteur manufacturier clé pour le Québec et le Canada qui doit constamment améliorer sa compétitivité, notamment par des investissements permettant le contrôle des opérations. Un équipement important et très énergivore dans le procédé de production de dioxyde de Titane est le four à arc électrique de réduction du minerai d’ilménite. Ce dernier utilise une grande quantité d’électricité et un agent réducteur pour fonctionner. Cet équipement est contrôlé par un système de commande automatique et par des opérateurs en fonction d’une cible d’opération établie par des métallurgistes. Ces cibles permettent de garantir le maintien de l’intégrité de l’équipement qui est opéré à haute température et la teneur en dioxyde de Titane du produit. L’objectif de ce projet est une amélioration de la performance du contrôle du procédé de réduction d’ilménite par l’utilisation de méthodes d’apprentissage automatique. Cette amélioration permettra le maintien de l’intégrité du four, une meilleure sécurité de son opération et une stabilité de la qualité des produits obtenus

Geometry reconstruction of rapidly moving specular surfaces relevant to fusion energy devices

This project seeks to play a role in making fusion energy a reality, a big step in energy decarbonization. The project is in collaboration with General Fusion, based in British Columbia, where a fusion reactor is being designed, based on a spinning cylinder of liquid lithium which is mechanically collapsed around a plasma to produce fusion, releasing energy the same way as the sun.

One design challenge is for the lithium to be collapsed perfectly, since any asymmetry in the collapse leads to inadequate pressure and temperature for fusion. The proposed MITACS partnership between General Fusion and the University of Waterloo is to characterize, in detail, the precise shape of the liquid lithium both before and during the collapse. There are significant imaging challenges present, both from the high speed of collapse, and the extreme temperatures at which the reactor operates, making this an outstanding research project.

Water is our Friend

This project supports relationship development with First Nations communities in British Columbia to facilitate collaboration on a larger flood-risk reduction project, which focuses on integrating Western expertise in architecture, engineering and social science with Indigenous Traditional Knowledge to create a new, collaborative approach for flood risk reduction in Indigenous communities in Canada. Relationship building prior to beginning a collaborative project with First Nations communities is necessary for successful adaptation and will ensure the community’s wants and needs for the project are understood. The project will be conducted in collaboration with the First Nations Emergency Services Society of British Columbia (FNESS), who have existing working relationships with many First Nations in British Columbia. Involvement in this project will engage FNESS in flood mitigation efforts that will be beneficial to their flood preparedness and response activities.

Evaluating the impact of climate change on forest watershed ecosystem services surrounding Cape Breton drinking water source areas

The trees surrounding the source drinking water lakes in Cape Breton Regional Municipality influence the pH and electrical conductivity of throughfall water in preliminary studies, particularly conifers like black spruce. The Kelly Lake Watershed that provides drinking water to the community of Louisbourg suffers from an acidity pulse each spring, potentially influenced by overland flow during the spring melt carrying associated activity from interactions with conifer needles. As low pH values help liberate metal ions, we want to see if the soil in these conifer dominated watersheds is leaching acidity, and possible metal ions, in the spring freshet. Climate change may push the black spruce further north, beyond its current distribution surrounding Kelly Lake, potentially alleviating the vernal acid pulses over time. Accelerating this transition to more favourable FES through stand manipulation may be a short-term management technique available to the CBRM Water Utility Managers.

The WRENCH Impact Story (Inner City Work-Study)

The W.R.E.N.C.H. (Winnipeg Repair Education and Cycling Hub) is the largest best equipped community bike shop in western Canada. The mission of The Wrench is to create stronger, healthier communities by removing barriers to building, repairing, and maintaining bicycles with a focus on educating youth. The WRENCH makes
bikes accessible by:
• Providing programming, education and resources for community members, groups and organization
• Supporting school and community bike shops
• Promoting bike use (The WRENCH, n.d.)
The WRENCH does this through a variety of community programs that focus on waste diversion, poverty
alleviation, and education.

The objectives of the internship are to support the staff and volunteers. As staff and volunteers continue to rebuild post-pandemic the intern will provide support through helping run and oversee various programs, events, and popup events.
The second objective is to create connections in the community. Through holding and planning workshops and community visits, the intern will create connections between schools, organizations and individuals.
The third objective is to educate individuals. The intern will help create learning opportunities through the delivery of workshops, events and community visits.

CreativePEI Administrative Systems Modernization Project

CreativePEI will undertake an internship to modernize and improve internal systems and processes such as HR admin, finance management, banking, data security, which will allow better processes and create more time for delivering on core mandate. These solutions will be shared and mapped to other local sector group NFPs.

The Influence of Compression Garments on Running Biomechanics & Soft-Tissue Vibrations in Female Athletes

This proposed research project will be performed to understand the influence of female apparel on running biomechanics, soft tissue vibrations, and responses to neuromuscular fatigue in prolonged running. There is an emerging and growing need in sporting goods research and development departments to study female-specific running patterns in order to create products that ensure comfort, reduce the risk of injury, and improve performance based on scientific evidence. This project will use wearable technology to monitor the influence of different compression garments on female-specific running biomechanics and physiology in outdoor, prolonged running. The partner organization would also like to become world-leading experts in the area of accuracy, usability and data analytics as related to wearable technology, and this project would be a catalyst to help them achieve this goal.

Évaluation économique et de l’implantation d’innovations pour l’adaptation des domiciles des personnes aînées vivant dans le Bas-Saint-Laurent (BSL)

Dans le cadre de la démarche Bien vieillir chez soi, cette recherche-action vise à implanter et mesurer les effets d’innovations articulées autour de deux applications que sont Hygiène 2.0 et MapIt. D’une part, Hygiène 2.0 offre une structure systématique de questionnement utilisable par la personne aînée elle-même ou ses proches conduisant à identifier soit des aides techniques permettant d’adapter son environnement tout facilitant l’hygiène corporelle à domicile, soit une situation plus complexe pouvant nécessiter l’intervention d’une personne ergothérapeute. D’autre part, MapIt est une application mobile produisant un rendu photoréaliste d’une pièce d’un domicile en moins de 5 minutes facilitant le travail et la communication professionnelle lorsqu’une personne aînée s’engage dans une démarche d’adaptation de son domicile. Ces applications peuvent atténuer des entraves à l’adaptation du domicile des personnes aînées vivant au BSL. La recherche-action vise à implanter ces innovations et à mesurer leurs effets, notamment économiques et occupationnels.

Learning causal world models at scale

In order to navigate the world, an autonomous agent must build a causal model to understand the effects of its actions. In many tasks (automated car driving, automated medicine), collecting causal data, by performing arbitrary actions for the sake of measuring their effect (interventions), can be impractical, expensive and even unethical. On the other hand, collecting data by observing human agents (observations), is often much cheaper, but it does not allow for measuring causal effects. The objective of this project is to expand the capabilities of current reinforcement learning algorithms to combine and exploit both interventional (causal) and observational (non-causal) data in a correct and efficient way, in order to benefit from the abundance of observational data in the world.